Using a set of machine learning diagnostic models to determine a diagnosis based on a skin tone of a patient

Abstract

Systems and methods are disclosed herein for determining a diagnosis based on a base skin tone of a patient. In an embodiment, the system receives a base skin tone image of a patient, generates a calibrated base skin tone image by calibrating the base skin tone image using a reference calibration profile, and determines a base skin tone of the patient based on the calibrated base skin tone image. The system receives a concern image of a portion of the patient's skin, and selects a set of machine learning diagnostic models from a plurality of sets of candidate machine learning diagnostic models based on the base skin tone of the patient, each of the sets of candidate machine learning diagnostic models trained to receive the concern image and output a diagnosis of a condition of the patient.

What is claimed is: 
     
         1 . A method comprising:
 generating a calibrated base skin tone image using an image of a patient and a reference calibration profile;   determining a base skin tone of the patient by applying a classification to an aggregate representation of the calibrated base skin tone image;   receiving a concern image of a portion of the patient's skin;   inputting at least the concern image into at least one machine learning model; and   receiving, as output from the at least one machine learning model, preliminary diagnostic information;   transforming the preliminary diagnostic information based on the base skin tone; and   determining a diagnosis based on the transformed preliminary diagnostic information.   
     
     
         2 . The method of  claim 1 , wherein the base skin tone is calibrated responsive to determining that the image of the patient satisfies a quality criterion. 
     
     
         3 . The method of  claim 1 , wherein the method further comprises:
 generating an adapted imaging profile based on the reference calibration profile and the base skin tone; and   calibrating the concern image using the adapted imaging profile.   
     
     
         4 . The method of  claim 1 , wherein the method further comprises selecting a set of machine learning diagnostic models from a plurality of sets of candidate machine learning diagnostic models based on the base skin tone of the patient, each of the sets of candidate machine learning diagnostic models trained to receive the concern image and output a diagnosis of a condition of the patient, and wherein the at least one machine learning model is a part of the selected set. 
     
     
         5 . The method of  claim 4 , wherein the method further comprises determining the classification that corresponds to the base skin tone, wherein selecting the set of machine learning diagnostic models comprises selecting a diagnosis classifier that corresponds to the classification, and wherein the method further comprises:
 inputting the concern image into the selected diagnosis classifier; and   receiving, as output from the selected diagnosis classifier, the preliminary diagnostic information.   
     
     
         6 . The method of  claim 1 , wherein the diagnosis is at least partially derived from the base skin tone image by inputting the base skin tone along with the concern image into the at least one machine learning model. 
     
     
         7 . The method of  claim 1 , wherein the method further comprises:
 determining whether the concern image is diagnosable based on the base skin tone; and   responsive to determining that the concern image is not diagnosable, outputting an indication that the concern image is not diagnosable.   
     
     
         8 . The method of  claim 1 , wherein the diagnosis comprises a probability that the patient has a condition. 
     
     
         9 . A computer program product for determining a diagnosis based on a base skin tone of a patient, the computer program product comprising a non-transitory computer-readable storage medium containing computer program code for:
 generating a calibrated base skin tone image using an image of a patient and a reference calibration profile;   determining a base skin tone of the patient by applying a classification to an aggregate representation of the calibrated base skin tone image;   receiving a concern image of a portion of the patient's skin;   inputting at least the concern image into at least one machine learning model; and   receiving, as output from the at least one machine learning model, preliminary diagnostic information;   transforming the preliminary diagnostic information based on the base skin tone; and   determining a diagnosis based on the transformed preliminary diagnostic information.   
     
     
         10 . The computer program product of  claim 9 , wherein the base skin tone is calibrated responsive to determining that the image of the patient satisfies a quality criterion. 
     
     
         11 . The computer program product of  claim 9 , wherein the computer program code is further for:
 generating an adapted imaging profile based on the reference calibration profile and the base skin tone; and   calibrating the concern image using the adapted imaging profile.   
     
     
         12 . The computer program product of  claim 9 , wherein the computer program code is further for selecting a set of machine learning diagnostic models from a plurality of sets of candidate machine learning diagnostic models based on the base skin tone of the patient, each of the sets of candidate machine learning diagnostic models trained to receive the concern image and output a diagnosis of a condition of the patient, and wherein the at least one machine learning model is a part of the selected set. 
     
     
         13 . The computer program product of  claim 12 , wherein selecting the set of machine learning diagnostic models comprises selecting a diagnosis classifier that corresponds to the classification, and wherein the computer program code is further for:
 inputting the concern image into the selected diagnosis classifier; and   receiving, as output from the selected diagnosis classifier, the preliminary diagnostic information.   
     
     
         14 . The computer program product of  claim 9 , wherein the diagnosis is at least partially derived from the base skin tone image by inputting the base skin tone along with the concern image into the at least one machine learning model. 
     
     
         15 . The computer program product of  claim 9 , wherein the computer program code is further for:
 determining whether the concern image is diagnosable based on the base skin tone; and   responsive to determining that the concern image is not diagnosable, outputting an indication that the concern image is not diagnosable.   
     
     
         16 . The computer program product of  claim 9 , wherein the diagnosis comprises a probability that the patient has a condition. 
     
     
         17 . A system comprising:
 a non-transitory computer-readable medium having memory with instructions encoded thereon; and   one or more processors that, when executing the instructions, are caused to perform operations comprising:
 generating a calibrated base skin tone image using an image of a patient and a reference calibration profile; 
 determining a base skin tone of the patient by applying a classification to an aggregate representation of the calibrated base skin tone image; 
 receiving a concern image of a portion of the patient's skin; 
 inputting at least the concern image into at least one machine learning model; and 
 receiving, as output from the at least one machine learning model, preliminary diagnostic information; 
 transforming the preliminary diagnostic information based on the base skin tone; and 
 determining a diagnosis based on the transformed preliminary diagnostic information. 
   
     
     
         18 . The system of  claim 17 , wherein the base skin tone is calibrated responsive to determining that the image of the patient satisfies a quality criterion. 
     
     
         19 . The system of  claim 17 , wherein the operations further comprise:
 generating an adapted imaging profile based on the reference calibration profile and the base skin tone; and   calibrating the concern image using the adapted imaging profile.   
     
     
         20 . The system of  claim 17 , wherein the operations further comprise selecting a set of machine learning diagnostic models from a plurality of sets of candidate machine learning diagnostic models based on the base skin tone of the patient, each of the sets of candidate machine learning diagnostic models trained to receive the concern image and output a diagnosis of a condition of the patient, and wherein the at least one machine learning model is a part of the selected set.